A unified neural network approach for steel beams patch load capacity

This work presents a neural networks modelling to forecast steel beam's patch load resistance. In preceding studies, neural network results have been compared and calibrated with experimental data and existing design formulae, showing a good agreement. Despite these results, the adopted method did not properly consider the differences in behaviour of slender, intermediate and compact beams. This paper introduces a new strategy based on a single neural network containing all the 155 experimental results. The Neural Network presented a maximum error value lower than 30%, while the existing formulas presented errors greater than 40%.